Privacy in the Age of Big Data, ML & Blockchains

Add to your list(s) Download to your calendar using vCal

• Pascal Berrang (University of Birmingham)
• Thursday 17 December 2020, 11:00-12:00
• Zoom (e-mail organiser for details).

If you have a question about this talk, please contact Andreea Radu.

Advances in Data Science and Machine Learning have led to a deluge of data required for the increasingly complex models and analyses in these fields. Industry and research agree that these tools have the potential to provide an immense improvement to our standard of living. In the field of biomedicine, for example, this technology is paving the way towards a more precise and personalised medicine. Similarly, blockchain technology is promising to revolutionise our financial sector by providing a more transparent, censorship-resistant way of transacting digital money. Both these developments have an important, albeit regularly overlooked commonality: they are applied to deal with highly sensitive, interdependent data.

In this talk, we present some of the privacy implications induced by these technologies. Picking up health data as one of the most sensitive types of data, we show how to quantify and protect the privacy of patients’ data in biomedical studies and Covid-19 apps. We introduce tailored solutions based on the perturbation of data and cryptographic constructions. We also analyse the privacy leakage of modern ML models and present future work on cross-blockchain financial privacy.

This talk is part of the Computer Security Seminars series.

This talk is included in these lists:

• Computer Science Departmental Series
• Computer Science Distinguished Seminars
• Computer Security Seminars
• Zoom (e-mail organiser for details)
• computer sience

Note that ex-directory lists are not shown.